logoalt Hacker News

kamranjontoday at 2:28 PM2 repliesview on HN

You might look at this and and be a bit disappointed by the performance against qwen and gemma models - but this is an entirely open source training pipeline, this is quite impressive and I don't think another model this performant exists with fully open source data and recipes alongside the weights.


Replies

hadlocktoday at 5:30 PM

>I don't think another model this performant exists with fully open source data and recipes alongside the weights

If you're already selling shovels, you might as well provide maps to the gold mine with every purchase.